Review of Current State of Artificial Intelligence/Machine Learning and Other Advanced Techniques Related to Air-to-Air Collision Risk Models (CRM) in the Terminal Airspace

Details

• Creators:
  Sherry, Lance ; Shortle, John ; Payan, Alexia P ; Harrison, Evan ; Thapa, Ashim Kumar ; Melgar, Alberto Cardenas ; Auguste, Yohan
• Corporate Creators:
  George Mason University ; Georgia Institute of Technology
• Corporate Contributors:
  United States. Department of Transportation. Federal Aviation Administration. Mike Monroney Aeronautical Center
• Subject/TRT Terms:
  • Collisions
  • Crash risk forecasting
  • Risk assessment
  • Machine learning
  • Artificial intelligence
  • Advanced vehicle control systems
• Publication/ Report Number:
  DOT/FAA/TC-23/37
• DOI:
  https://doi.org/10.21949/1528218
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Contracting Officer:
  Li, Huasheng
• Corporate Publisher:
  United States. Department of Transportation. Federal Aviation Administration. William J. Hughes Technical Center
• Abstract:
  Collision Risk Models (CRM) are used by regulatory safety agencies to determine the safe separation minima and monitor the air-to-air collision risk level of an airspace. CRMs estimate the expected number of aircraft collisions and "total" risk for a given air traffic concept-of-operation (e.g., parallel approaches). The fidelity of the models, and assumptions used in the models, are determined by the required confidence interval required for the safety analysis, the capabilities of current analytical and simulation methods, availability of empirical data sets, and the capabilities of computational resources. This paper provides an overview of the state-of-the-art CRMs for terminal area operations. Opportunities to apply recently developed artificial intelligence/machine learning (AI/ML), and data analytics methods such as analytical and rare-event simulation methods, availability of empirical data sets, and leverage available computational resources are identified.
• Format:
  PDF
• Funding:
  693KA9-20-D-00004DTFACT-14-D-00004
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/67526/dot_67526_DS1.pdf
• File Type:
  [PDF - 1.14 MB]
• Collection(s):
  Autonomous Vehicles ; FAA William J. Hughes Technical Center for Advanced Aerospace
• Main Document Checksum:
  urn:sha-512:8a7bc4c7f4b6cf39e888c26fdbd0e0847c04dedcc51db5a7a877ef69ea533f33702bfd54642f89efb209fb0ed39c1dc978ac9ca7cfdcd01dd03b5a54ef4c7bf0